This repository contains the Hugging Face checkpoint used by Xiaomi-Robotics-1 for VLABench evaluation. It includes the model weights, custom Transformers model and processor code, tokenizer files, and VLABench action normalization statistics. The custom model and processor must be loaded with trustremotecode=True. For the VLABench simulation environment, follow the companion source repository at evalvlabench/README.md. The evaluation client uses a separate vlabench conda environment with Python 3.10 and the pinned MuJoCo / dmcontrol dependencies described there. For reproducible multi-GPU evaluation, use the standard multi-server launcher in the companion Xiaomi-Robotics-1 source…
Open weights
apache-2.0
5.1B parameters
Xiaomi-TabLDM: A Tabular Large Data Foundation Model For Classification and Regression via In-Context Learning English This repository is the official implementation of Xiaomi-TabLDM. Tabular foundation models establish a general prediction paradigm based on in-context learning. Given labeled samples from a downstream dataset as context, a single pretrained model can make predictions directly without task-specific training. Building on this paradigm, we introduce Xiaomi-TabLDM, a tabular large data foundation model for classification and regression via in-context learning, which delivers superior prediction accuracy without requiring task-specific fine-tuning. Pretrained exclusively on…
Open weights
mit
custom
Open weights
Open weights
262,144 tokens
This model is a fine-tune of specialized for telecom-customer-service-chat, targeting the Guangdong Telecom 10000 hotline smart customer-service agent. Instead of replying like a generic assistant, the model is tuned to act as a slots, dispatching the right business tool, and producing compliant, warm and concise service dialogue. - Intent recognition & routing — accurately identifies user intents (账单查询、流量查询、装移机、报障、宽带续费、投诉等) and dispatches to the correct skill / candidate task. - Slot clarification — actively asks for missing required slots only when the user's intent is unclear, avoiding redundant or misleading questions. - Tool calling & task dispatch — outputs structured toolcall /…
Open weights
Open weights
YANchor-4B is a general-purpose recurrent model that preserves crucial memory as ANchors for retrieval during subsequent reasoning. Its multidimensional memory mechanism enables effective long-horizon reasoning with O(N) generation time and O(1) history-state memory. For example, on challenging math problems, YANchor achieves 82.93% mean pass@1 on AIME 2024–2026 and 63.64% on HMMT, substantially outperforming linear-time, constant-state counterparts, including 7B–14B models. YANchor delivers several-fold higher batched long-generation throughput than Transformer and hybrid baselines on H100. Evaluations across dozens of benchmarks demonstrate its superiority in general-purpose capabilities.…
Open weights
other
4.6B parameters
262,144 tokens
Open weights
Open weights
Study the Word as it was spoken — verse by verse, tongue by tongue. YahBible is a free desktop app for deep study and comparison of the Bible and the other sacred literatures — a custom reader, a Hebrew/Greek/Aramaic word engine, Strong's + interlinear, It runs right out of the box on Windows — download one file and go. 1. Download YahBible.exe (button above, or the Files and versions tab). 2. Double-click it. 3. It opens in your browser at 127.0.0.1. That's it. Or install it for a permanent home + a Start-menu / taskbar icon: run YahBible.exe and choose Install, then pin the icon. On first run it downloads its study library from this repo (~1.2 GB), so the app is usable within moments; the…
Open weights
other
The whole counsel of Scripture — to read, search and study, in the original Hebrew, Greek and Aramaic, on any device, offline. Free for life. Grab it first, then keep reading while it downloads. It's free — and it stays free. yes · requires payment or subscription · no. Only YahBible is fully offline — including its AI search and reasoning — and stays free with no trial or subscription. Other apps' names belong to their owners. The King James Bible with 120+ translations, verse for verse. Search however you remember a passage — "3:16 John", "the 23rd Psalm" — and switch versions without losing your place. Open any commandment in the centre: its Scripture, what it forbids, how to keep it…
Open weights
cc-by-nc-4.0
Open weights
static quants of https://huggingface.co/rwang220/Yida-Model-14B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And…
Open weights
apache-2.0
transformers
English · 中文 ds4 is a native C/CUDA inference engine plus an offline toolchain that runs DeepSeek V4.1 Flash on a single NVIDIA DGX Spark (GB10, 128 GB unified memory). Everything described here is our own work: the vector-quantization format, the solvers that produce the sidecar and the post-training file, the CUDA kernels, and the rulers we judge all of it with. The model architecture is DeepSeek's and is not re-explained here — read the official release for that. How to read this page. It unfolds in five steps; stop wherever you have what you need. 1. The numbers — what runs, how fast, how close to the original. 2. Three convictions — why the system is shaped this way. 3. The…
Open weights
mit
Open weights
Open weights
cc-by-nc-4.0
DHQ = Dual-Head Quant. Z-Image-Engineer-V6 (a Qwen3-4B fine-tune that is both a Z-Image text encoder and a prompt writer), quantized so that every tensor gets the precision that matters to what the Z-Image DiT actually reads (measured per tensor with gradients through the DiT's text input), with an importance matrix computed on V6 itself. Each file is exactly the size of the standard llama.cpp file of the same name, and the text-encoder error is lower at every level. Tuned for Z-Image only. It was not measured with FLUX.2 [klein] 4B; for klein use the plain Qwen3-4B file in DHQ files are quantized for use as a diffusion model's text encoder: each tensor's precision is chosen by how much its…
Open weights
apache-2.0
Access requested at publisher
ZDTaichu5.0-9B is a multimodal foundation model for general visual understanding, spatial reasoning, agentic tool use, and embodied-AI research. It combines a Qwen3.5-9B language backbone with a C-RADIOv4-H vision encoder, supports text, images and videos with any-resolution visual input. Within the 10B-scale general-purpose VLMs compared in this release blog, ZDTaichu5.0-9B retains first-tier general visual understanding while supporting spatial reasoning, high-level embodied VLM reasoning, and agent tasks under the reported evaluation settings. Rather than trading broad visual competence for specialization, it layers a more comprehensive spatial, embodied, and agent capability profile on…
Open weights
Open weights
7.4B parameters
262,144 tokens
mlx
Open weights
Open weights
mit
static quants of https://huggingface.co/z51722369/ZOZ-Function-Master-3B-LongContext For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/ZOZ-Function-Master-3B-LongContext-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
Open weights
transformers
weighted/imatrix quants of https://huggingface.co/z51722369/ZOZ-Function-Master-3B-LongContext For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/ZOZ-Function-Master-3B-LongContext-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
Open weights
transformers
